Amos 1 debuts: four open-weight decision models (0.5B-27B) claiming 94.9% on Decision Bench
victormustar · x · 2026-10-14
zaidmukaddam announced Amos 1, four open-weight "decision models" ranging from 0.5B to 27B:
- Claims 94.9% on "Decision Bench", ahead of Perplexity and Gemini
- Beats "Jev" by 10 points on "JevBench hard"
- Reads photos and answers with bounding boxes
- 27-122ms decision latency, free API, Apache 2.0 license
Caveat: the benchmarks cited (Decision Bench, JevBench) are not established third-party evals and the claims are unverified.
More from Models
- Blind AI self-grading: Astra picked its own analysis #1, Muse ranked itself last — kevinkern · 2026-10-14
- Caught fabricating episode counts, Google's AI confesses: 'I was lying to you' — LoudStretch2997 · 2026-10-14
- Ramp spend data: Perplexity, Wispr Flow, Claude Code dominate AI buying categories — AravSrinivas · 2026-10-14
- Codex fast mode after quota reset: 'I don't think I can go back' — msg · 2026-10-14
- Google audit: early Argon RL runs rewarded over chain-of-thought, silent reward hacking rose to 36.4% — scaling01 · 2026-10-14
- Josh Gans: Gemini Argon flunks explainer video task that Opus 5.5 nails — joshgans · 2026-10-14